| Presentation | 2022-03-08 Evaluation of Data Augmentation Methods Considering Occlusion Region for 3D Point Cloud Classification Shiori Maki, Kenji Kanai, Shota Hirose, Heming Sun, Jiro Katto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, research of point cloud classification using deep learning has been improved. In this paper, we propose a data augmentation method for building a robust model against occlusions. The proposed model is inspired by the 2D data augmentation methods, such as random erasing and cutout methods. Through the performance evaluations, we verify that the proposed method can contribute to improvement of classification accuracy even if a part of point cloud is lacked due to the occlusion. In addition, we also verify availability of the proposed method against real data and adversarial data that intentionally drops important points. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Point Cloud / Deep Learning / Data Augmentation / Digital Twin |
| Paper # | SeMI2021-91 |
| Date of Issue | 2022-02-28 (SeMI) |
| Conference Information | |
| Committee | SeMI / IPSJ-MBL / IPSJ-UBI |
|---|---|
| Conference Date | 2022/3/7(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Koji Yamamoto(Kyoto Univ.) |
| Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) |
| Secretary | Kazuya Monden(Cyber Univ.) / Yasunori Owada(Waseda Univ.) / (Osaka Univ.) |
| Assistant | Yuki Katsumata(NTT DOCOMO) / Akihito Taya(Aoyama Gakuin Univ.) / Yu Nakayama(Tokyo Univ. of Agri. and Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Sensor Network and Mobile Intelligence / Special Interest Group on Mobile Computing and Smart Society System / Special Interest Group on Ubiquitous Computing System |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Evaluation of Data Augmentation Methods Considering Occlusion Region for 3D Point Cloud Classification |
| Sub Title (in English) | |
| Keyword(1) | Point Cloud |
| Keyword(2) | Deep Learning |
| Keyword(3) | Data Augmentation |
| Keyword(4) | Digital Twin |
| 1st Author's Name | Shiori Maki |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Kenji Kanai |
| 2nd Author's Affiliation | Waseda University(Waseda Univ.) |
| 3rd Author's Name | Shota Hirose |
| 3rd Author's Affiliation | Waseda University(Waseda Univ.) |
| 4th Author's Name | Heming Sun |
| 4th Author's Affiliation | Waseda University(Waseda Univ.) |
| 5th Author's Name | Jiro Katto |
| 5th Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2022-03-08 |
| Paper # | SeMI2021-91 |
| Volume (vol) | vol.121 |
| Number (no) | SeMI-411 |
| Page | pp.pp.47-52(SeMI), |
| #Pages | 6 |
| Date of Issue | 2022-02-28 (SeMI) |